CILC: Cryptographically-secure Inter-agent Loop Closure Candidate Detection for Multi-Agent Collaborative SLAM
This work addresses the privacy threat of information leakage from global descriptors in collaborative SLAM, which is critical for multi-robot systems operating in adversarial or untrusted environments.
The paper demonstrates that a compromised robot in multi-agent SLAM can reconstruct an honest agent's imagery and trajectory from its global descriptor broadcasts, and proposes CILC, a system using Secure Multi-Party Computation to detect inter-agent loop closure candidates without exposing descriptors. Experiments show CILC remains real-time and communication-feasible across visual and LiDAR modalities while mitigating information leakage.
Multi-agent Simultaneous Localization and Mapping (SLAM) and collaborative SLAM (CSLAM) require robots to continuously exchange global descriptors (GDs) to detect inter-agent loop closures (ILCs). While encrypted radios protect this traffic from external eavesdroppers, they offer no protection against a compromised swarm member. We show this threat is concrete by demonstrating how a corrupted agent can reconstruct approximations of an honest agent's imagery and trajectory from its public GD broadcasts. To address this, we propose CILC (Cryptographically-secure Inter-agent Loop Closure candidate detection), a first-of-its-kind system leveraging Secure Multi-Party Computation (SMPC) to detect ILC candidates without exchanging GDs in the clear. Rather than securing the entire CSLAM pipeline, we apply SMPC only to ILC candidate detection (i.e., GD similarity comparison), a privacy-sensitive yet computationally lightweight step, yielding an advantageous privacy-to-overhead trade-off. We validate in both simulation and hardware experiments that CILC remains real-time and communication-feasible across multimodal GDs (visual and LiDAR), while mitigating information leakage to a compromised swarm agent.